AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Clustering Convolutional Kernels to Compress Deep Neural Networks

Sanghyun Son, Seungjun Nah, Kyoung Mu Lee

ECCV 2018 · Architectures and efficiency › CNN design · approach: CNN filter pruning · 85 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase number of centroids k from 128 to 1024 (ablation)VGG-16 kernel clustering · CIFAR-10 testerror rate (%): 6.24 -> 6.01Improved
increase centroids from 128 to 1024 (ablation)ResNet-56 kernel clustering · CIFAR-10 testerror rate (%): 6.76 -> 6.30Improved
add multi clustering with 2 groups (ablation)VGG-16-C64 · CIFAR-10 testerror rate (%): 6.44 -> 6.27Improved
add per-layer multi clustering (M13) (ablation)VGG-16-C64 · CIFAR-10 testerror rate (%): 6.44 -> 6.21Improved
add per-layer multi clustering instead of 2 groups at k=256 (ablation)VGG-16-C256 · CIFAR-10 testerror rate (%): 6.16 -> 6.10Improved
add transform invariant clustering with vertical flips (TIC2) (ablation)VGG-16-C128 · CIFAR-10 testerror rate (%): 6.23 -> 5.92Improved
add horizontal flips too (TIC4, 64 centroids) (ablation)VGG-16-TIC2 · CIFAR-10 testerror rate (%): 5.92 -> 6.25Hurt
add rotations too (TIC8, 32 centroids) (ablation)VGG-16-TIC · CIFAR-10 testerror rate (%): 6.25 -> 6.51Hurt
add filter pruning before clustering (ablation)VGG-16-C512 · CIFAR-10 test (with pruning)error rate (%): 6.16 -> 5.99Improved
add simple pruning before clustering (ablation)VGG-16-C512 · CIFAR-10 test (with pruning)error rate (%): 6.16 -> 6.13Improved
remove scale parameters (N) at 128 centroids (ablation)DenseNet-BC-C128 · CIFAR-10 test (DenseNet-BC)error rate (%): 4.51 -> 4.44Improved
remove scale parameters (N) at 64 centroids (ablation)DenseNet-BC-C64 · CIFAR-10 test (DenseNet-BC)error rate (%): 4.50 -> 4.60Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy